summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/aufs/cpup.c66
-rw-r--r--fs/aufs/dir.c5
-rw-r--r--fs/aufs/export.c2
-rw-r--r--fs/aufs/f_op.c16
-rw-r--r--fs/aufs/fstype.h1
-rw-r--r--fs/aufs/i_op.c6
-rw-r--r--fs/aufs/module.c2
-rw-r--r--fs/aufs/module.h1
-rw-r--r--fs/aufs/posix_acl.c1
-rw-r--r--fs/aufs/vfsub.c18
-rw-r--r--fs/aufs/vfsub.h21
-rw-r--r--fs/btrfs/backref.c10
-rw-r--r--fs/btrfs/delayed-inode.c3
-rw-r--r--fs/btrfs/delayed-inode.h2
-rw-r--r--fs/btrfs/inode.c16
-rw-r--r--fs/btrfs/ioctl.c119
-rw-r--r--fs/btrfs/volumes.c28
-rw-r--r--fs/cifs/cifs_debug.c2
-rw-r--r--fs/cifs/cifs_debug.h9
-rw-r--r--fs/cifs/cifsencrypt.c2
-rw-r--r--fs/cifs/connect.c2
-rw-r--r--fs/cifs/readdir.c1
-rw-r--r--fs/cifs/transport.c6
-rw-r--r--fs/devpts/inode.c20
-rw-r--r--fs/ext4/balloc.c7
-rw-r--r--fs/ext4/ialloc.c6
-rw-r--r--fs/ext4/move_extent.c15
-rw-r--r--fs/ext4/resize.c2
-rw-r--r--fs/hugetlbfs/inode.c19
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c8
-rw-r--r--fs/nfs/inode.c54
-rw-r--r--fs/nfs/nfs4proc.c2
-rw-r--r--fs/overlayfs/copy_up.c41
-rw-r--r--fs/overlayfs/inode.c13
-rw-r--r--fs/overlayfs/readdir.c3
-rw-r--r--fs/overlayfs/super.c5
-rw-r--r--fs/proc/array.c2
-rw-r--r--fs/proc/base.c21
-rw-r--r--fs/proc/namespaces.c4
-rw-r--r--fs/proc/task_mmu.c7
-rw-r--r--fs/timerfd.c2
-rw-r--r--fs/udf/inode.c15
-rw-r--r--fs/udf/unicode.c21
-rw-r--r--fs/xfs/libxfs/xfs_format.h2
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c12
-rw-r--r--fs/xfs/xfs_buf.c17
46 files changed, 489 insertions, 148 deletions
diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c
index a34648874..d34a6d283 100644
--- a/fs/aufs/cpup.c
+++ b/fs/aufs/cpup.c
@@ -512,6 +512,55 @@ out:
return err;
}
+/*
+ * regardless 'acl' option, reset all ACL.
+ * All ACL will be copied up later from the original entry on the lower branch.
+ */
+static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode)
+{
+ int err;
+ struct dentry *h_dentry;
+ struct inode *h_inode;
+
+ h_dentry = h_path->dentry;
+ h_inode = d_inode(h_dentry);
+ /* forget_all_cached_acls(h_inode)); */
+ err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS);
+ AuTraceErr(err);
+ if (!err)
+ err = vfsub_acl_chmod(h_inode, mode);
+
+ AuTraceErr(err);
+ return err;
+}
+
+static int au_do_cpup_dir(struct au_cp_generic *cpg, struct dentry *dst_parent,
+ struct inode *h_dir, struct path *h_path)
+{
+ int err;
+ struct inode *dir, *inode;
+
+ err = vfsub_removexattr(h_path->dentry, XATTR_NAME_POSIX_ACL_DEFAULT);
+ AuTraceErr(err);
+ if (err == -EOPNOTSUPP)
+ err = 0;
+ if (unlikely(err))
+ goto out;
+
+ /*
+ * strange behaviour from the users view,
+ * particularry setattr case
+ */
+ dir = d_inode(dst_parent);
+ if (au_ibstart(dir) == cpg->bdst)
+ au_cpup_attr_nlink(dir, /*force*/1);
+ inode = d_inode(cpg->dentry);
+ au_cpup_attr_nlink(inode, /*force*/1);
+
+out:
+ return err;
+}
+
static noinline_for_stack
int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent,
struct au_cpup_reg_attr *h_src_attr)
@@ -524,7 +573,7 @@ int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent,
struct au_dtime dt;
struct path h_path;
struct dentry *h_src, *h_dst, *h_parent;
- struct inode *h_inode, *h_dir, *dir, *inode;
+ struct inode *h_inode, *h_dir;
struct super_block *sb;
/* bsrc branch can be ro/rw. */
@@ -564,17 +613,8 @@ int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent,
case S_IFDIR:
isdir = 1;
err = vfsub_mkdir(h_dir, &h_path, mode);
- if (!err) {
- /*
- * strange behaviour from the users view,
- * particularry setattr case
- */
- dir = d_inode(dst_parent);
- if (au_ibstart(dir) == cpg->bdst)
- au_cpup_attr_nlink(dir, /*force*/1);
- inode = d_inode(cpg->dentry);
- au_cpup_attr_nlink(inode, /*force*/1);
- }
+ if (!err)
+ err = au_do_cpup_dir(cpg, dst_parent, h_dir, &h_path);
break;
case S_IFLNK:
err = au_do_cpup_symlink(&h_path, h_src, h_dir);
@@ -591,6 +631,8 @@ int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent,
AuIOErr("Unknown inode type 0%o\n", mode);
err = -EIO;
}
+ if (!err)
+ err = au_reset_acl(h_dir, &h_path, mode);
mnt_flags = au_mntflags(sb);
if (!au_opt_test(mnt_flags, UDBA_NONE)
diff --git a/fs/aufs/dir.c b/fs/aufs/dir.c
index 8a619062a..a994e0862 100644
--- a/fs/aufs/dir.c
+++ b/fs/aufs/dir.c
@@ -237,11 +237,13 @@ static int do_open_dir(struct file *file, int flags, struct file *h_file)
int err;
aufs_bindex_t bindex, btail;
struct dentry *dentry, *h_dentry;
+ struct vfsmount *mnt;
FiMustWriteLock(file);
AuDebugOn(h_file);
err = 0;
+ mnt = file->f_path.mnt;
dentry = file->f_path.dentry;
file->f_version = d_inode(dentry)->i_version;
bindex = au_dbstart(dentry);
@@ -253,6 +255,9 @@ static int do_open_dir(struct file *file, int flags, struct file *h_file)
if (!h_dentry)
continue;
+ err = vfsub_test_mntns(mnt, h_dentry->d_sb);
+ if (unlikely(err))
+ break;
h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
if (IS_ERR(h_file)) {
err = PTR_ERR(h_file);
diff --git a/fs/aufs/export.c b/fs/aufs/export.c
index 4ce7732b7..7f6fec61f 100644
--- a/fs/aufs/export.c
+++ b/fs/aufs/export.c
@@ -597,7 +597,7 @@ aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len,
ino = decode_ino(fh + Fh_ino);
/* it should never happen */
if (unlikely(ino == AUFS_ROOT_INO))
- goto out;
+ goto out_unlock;
dir_ino = decode_ino(fh + Fh_dir_ino);
dentry = decode_by_ino(sb, ino, dir_ino);
diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c
index c1be75cb0..2baacd7a6 100644
--- a/fs/aufs/f_op.c
+++ b/fs/aufs/f_op.c
@@ -16,7 +16,7 @@ int au_do_open_nondir(struct file *file, int flags, struct file *h_file)
{
int err;
aufs_bindex_t bindex;
- struct dentry *dentry;
+ struct dentry *dentry, *h_dentry;
struct au_finfo *finfo;
struct inode *h_inode;
@@ -29,10 +29,19 @@ int au_do_open_nondir(struct file *file, int flags, struct file *h_file)
memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop));
atomic_set(&finfo->fi_mmapped, 0);
bindex = au_dbstart(dentry);
- if (!h_file)
+ if (!h_file) {
+ h_dentry = au_h_dptr(dentry, bindex);
+ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
+ if (unlikely(err))
+ goto out;
h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
- else
+ } else {
+ h_dentry = h_file->f_path.dentry;
+ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
+ if (unlikely(err))
+ goto out;
get_file(h_file);
+ }
if (IS_ERR(h_file))
err = PTR_ERR(h_file);
else {
@@ -50,6 +59,7 @@ int au_do_open_nondir(struct file *file, int flags, struct file *h_file)
/* file->f_ra = h_file->f_ra; */
}
+out:
return err;
}
diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h
index e429a8b17..725b2ffff 100644
--- a/fs/aufs/fstype.h
+++ b/fs/aufs/fstype.h
@@ -240,7 +240,6 @@ static inline int au_test_hfsplus(struct super_block *sb __maybe_unused)
static inline int au_test_fs_unsuppoted(struct super_block *sb)
{
return
- au_test_fuse(sb) || /* for a security reason, temporarily */
#ifndef CONFIG_AUFS_BR_RAMFS
au_test_ramfs(sb) ||
#endif
diff --git a/fs/aufs/i_op.c b/fs/aufs/i_op.c
index 1c634bab9..6e50526d8 100644
--- a/fs/aufs/i_op.c
+++ b/fs/aufs/i_op.c
@@ -963,6 +963,12 @@ static int aufs_setattr(struct dentry *dentry, struct iattr *ia)
break;
}
}
+ /*
+ * regardless aufs 'acl' option setting.
+ * why don't all acl-aware fs call this func from their ->setattr()?
+ */
+ if (!err && (ia->ia_valid & ATTR_MODE))
+ err = vfsub_acl_chmod(a->h_inode, ia->ia_mode);
if (!err)
au_cpup_attr_changeable(inode);
diff --git a/fs/aufs/module.c b/fs/aufs/module.c
index ec12f2e66..8a28377c5 100644
--- a/fs/aufs/module.c
+++ b/fs/aufs/module.c
@@ -95,7 +95,7 @@ MODULE_PARM_DESC(brs, "use <sysfs>/fs/aufs/si_*/brN");
module_param_named(brs, sysaufs_brs, int, S_IRUGO);
/* this module parameter has no meaning when USER_NS is disabled */
-static bool au_userns;
+bool au_userns;
MODULE_PARM_DESC(allow_userns, "allow unprivileged to mount under userns");
module_param_named(allow_userns, au_userns, bool, S_IRUGO);
diff --git a/fs/aufs/module.h b/fs/aufs/module.h
index b129ad4b6..bb8644730 100644
--- a/fs/aufs/module.h
+++ b/fs/aufs/module.h
@@ -18,6 +18,7 @@ struct seq_file;
/* module parameters */
extern int sysaufs_brs;
+extern bool au_userns;
/* ---------------------------------------------------------------------- */
diff --git a/fs/aufs/posix_acl.c b/fs/aufs/posix_acl.c
index 1c19e629b..a3c442c08 100644
--- a/fs/aufs/posix_acl.c
+++ b/fs/aufs/posix_acl.c
@@ -7,7 +7,6 @@
*/
#include <linux/fs.h>
-#include <linux/posix_acl.h>
#include "aufs.h"
struct posix_acl *aufs_get_acl(struct inode *inode, int type)
diff --git a/fs/aufs/vfsub.c b/fs/aufs/vfsub.c
index f072c59c0..89f999c97 100644
--- a/fs/aufs/vfsub.c
+++ b/fs/aufs/vfsub.c
@@ -7,10 +7,28 @@
*/
#include <linux/namei.h>
+#include <linux/nsproxy.h>
#include <linux/security.h>
#include <linux/splice.h>
+#include "../fs/mount.h"
#include "aufs.h"
+#ifdef CONFIG_AUFS_BR_FUSE
+int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb)
+{
+ struct nsproxy *ns;
+
+ if (!au_test_fuse(h_sb) || !au_userns)
+ return 0;
+
+ ns = current->nsproxy;
+ /* no {get,put}_nsproxy(ns) */
+ return real_mount(mnt)->mnt_ns == ns->mnt_ns ? 0 : -EACCES;
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
int vfsub_update_h_iattr(struct path *h_path, int *did)
{
int err;
diff --git a/fs/aufs/vfsub.h b/fs/aufs/vfsub.h
index a7d8a1cf9..f2e1c49af 100644
--- a/fs/aufs/vfsub.h
+++ b/fs/aufs/vfsub.h
@@ -13,6 +13,7 @@
#include <linux/fs.h>
#include <linux/mount.h>
+#include <linux/posix_acl.h>
#include <linux/xattr.h>
#include "debug.h"
@@ -63,6 +64,12 @@ static inline int vfsub_native_ro(struct inode *inode)
|| IS_IMMUTABLE(inode);
}
+#ifdef CONFIG_AUFS_BR_FUSE
+int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb);
+#else
+AuStubInt0(vfsub_test_mntns, struct vfsmount *mnt, struct super_block *h_sb);
+#endif
+
/* ---------------------------------------------------------------------- */
int vfsub_update_h_iattr(struct path *h_path, int *did);
@@ -202,6 +209,20 @@ static inline int vfsub_update_time(struct inode *h_inode, struct timespec *ts,
/* no vfsub_update_h_iattr() since we don't have struct path */
}
+#ifdef CONFIG_FS_POSIX_ACL
+static inline int vfsub_acl_chmod(struct inode *h_inode, umode_t h_mode)
+{
+ int err;
+
+ err = posix_acl_chmod(h_inode, h_mode);
+ if (err == -EOPNOTSUPP)
+ err = 0;
+ return err;
+}
+#else
+AuStubInt0(vfsub_acl_chmod, struct inode *h_inode, umode_t h_mode);
+#endif
+
long vfsub_splice_to(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index d453d62ab..e2f659dc5 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1417,7 +1417,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
read_extent_buffer(eb, dest + bytes_left,
name_off, name_len);
if (eb != eb_in) {
- btrfs_tree_read_unlock_blocking(eb);
+ if (!path->skip_locking)
+ btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
}
ret = btrfs_find_item(fs_root, path, parent, 0,
@@ -1437,9 +1438,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
eb = path->nodes[0];
/* make sure we can use eb after releasing the path */
if (eb != eb_in) {
- atomic_inc(&eb->refs);
- btrfs_tree_read_lock(eb);
- btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ if (!path->skip_locking)
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ path->nodes[0] = NULL;
+ path->locks[0] = 0;
}
btrfs_release_path(path);
iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index e0941fbb9..02b934d0e 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1694,7 +1694,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
*
*/
int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
- struct list_head *ins_list)
+ struct list_head *ins_list, bool *emitted)
{
struct btrfs_dir_item *di;
struct btrfs_delayed_item *curr, *next;
@@ -1738,6 +1738,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
if (over)
return 1;
+ *emitted = true;
}
return 0;
}
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index f70119f25..0167853c8 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
int btrfs_should_delete_dir_index(struct list_head *del_list,
u64 index);
int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
- struct list_head *ins_list);
+ struct list_head *ins_list, bool *emitted);
/* for init */
int __init btrfs_delayed_inode_init(void);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a70c5790f..54b5f0de6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5741,6 +5741,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
char *name_ptr;
int name_len;
int is_curr = 0; /* ctx->pos points to the current index? */
+ bool emitted;
/* FIXME, use a real flag for deciding about the key type */
if (root->fs_info->tree_root == root)
@@ -5769,6 +5770,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
if (ret < 0)
goto err;
+ emitted = false;
while (1) {
leaf = path->nodes[0];
slot = path->slots[0];
@@ -5848,6 +5850,7 @@ skip:
if (over)
goto nopos;
+ emitted = true;
di_len = btrfs_dir_name_len(leaf, di) +
btrfs_dir_data_len(leaf, di) + sizeof(*di);
di_cur += di_len;
@@ -5860,11 +5863,20 @@ next:
if (key_type == BTRFS_DIR_INDEX_KEY) {
if (is_curr)
ctx->pos++;
- ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+ ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
if (ret)
goto nopos;
}
+ /*
+ * If we haven't emitted any dir entry, we must not touch ctx->pos as
+ * it was was set to the termination value in previous call. We assume
+ * that "." and ".." were emitted if we reach this point and set the
+ * termination value as well for an empty directory.
+ */
+ if (ctx->pos > 2 && !emitted)
+ goto nopos;
+
/* Reached end of directory/root. Bump pos past the last item. */
ctx->pos++;
@@ -7985,6 +7997,7 @@ static void btrfs_endio_direct_read(struct bio *bio)
kfree(dip);
+ dio_bio->bi_error = bio->bi_error;
dio_end_io(dio_bio, bio->bi_error);
if (io_bio->end_io)
@@ -8030,6 +8043,7 @@ out_test:
kfree(dip);
+ dio_bio->bi_error = bio->bi_error;
dio_end_io(dio_bio, bio->bi_error);
bio_put(bio);
}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index da94138eb..08fd3f0f3 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2782,24 +2782,29 @@ out:
static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
{
struct page *page;
- struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
page = grab_cache_page(inode->i_mapping, index);
if (!page)
- return NULL;
+ return ERR_PTR(-ENOMEM);
if (!PageUptodate(page)) {
- if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
- 0))
- return NULL;
+ int ret;
+
+ ret = btrfs_readpage(NULL, page);
+ if (ret)
+ return ERR_PTR(ret);
lock_page(page);
if (!PageUptodate(page)) {
unlock_page(page);
page_cache_release(page);
- return NULL;
+ return ERR_PTR(-EIO);
+ }
+ if (page->mapping != inode->i_mapping) {
+ unlock_page(page);
+ page_cache_release(page);
+ return ERR_PTR(-EAGAIN);
}
}
- unlock_page(page);
return page;
}
@@ -2811,17 +2816,31 @@ static int gather_extent_pages(struct inode *inode, struct page **pages,
pgoff_t index = off >> PAGE_CACHE_SHIFT;
for (i = 0; i < num_pages; i++) {
+again:
pages[i] = extent_same_get_page(inode, index + i);
- if (!pages[i])
- return -ENOMEM;
+ if (IS_ERR(pages[i])) {
+ int err = PTR_ERR(pages[i]);
+
+ if (err == -EAGAIN)
+ goto again;
+ pages[i] = NULL;
+ return err;
+ }
}
return 0;
}
-static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+static int lock_extent_range(struct inode *inode, u64 off, u64 len,
+ bool retry_range_locking)
{
- /* do any pending delalloc/csum calc on src, one way or
- another, and lock file content */
+ /*
+ * Do any pending delalloc/csum calculations on inode, one way or
+ * another, and lock file content.
+ * The locking order is:
+ *
+ * 1) pages
+ * 2) range in the inode's io tree
+ */
while (1) {
struct btrfs_ordered_extent *ordered;
lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
@@ -2839,8 +2858,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
if (ordered)
btrfs_put_ordered_extent(ordered);
+ if (!retry_range_locking)
+ return -EAGAIN;
btrfs_wait_ordered_range(inode, off, len);
}
+ return 0;
}
static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
@@ -2865,15 +2887,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
}
-static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
- struct inode *inode2, u64 loff2, u64 len)
+static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+ struct inode *inode2, u64 loff2, u64 len,
+ bool retry_range_locking)
{
+ int ret;
+
if (inode1 < inode2) {
swap(inode1, inode2);
swap(loff1, loff2);
}
- lock_extent_range(inode1, loff1, len);
- lock_extent_range(inode2, loff2, len);
+ ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
+ if (ret)
+ return ret;
+ ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
+ if (ret)
+ unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
+ loff1 + len - 1);
+ return ret;
}
struct cmp_pages {
@@ -2889,11 +2920,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
for (i = 0; i < cmp->num_pages; i++) {
pg = cmp->src_pages[i];
- if (pg)
+ if (pg) {
+ unlock_page(pg);
page_cache_release(pg);
+ }
pg = cmp->dst_pages[i];
- if (pg)
+ if (pg) {
+ unlock_page(pg);
page_cache_release(pg);
+ }
}
kfree(cmp->src_pages);
kfree(cmp->dst_pages);
@@ -2954,6 +2989,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
src_page = cmp->src_pages[i];
dst_page = cmp->dst_pages[i];
+ ASSERT(PageLocked(src_page));
+ ASSERT(PageLocked(dst_page));
addr = kmap_atomic(src_page);
dst_addr = kmap_atomic(dst_page);
@@ -3066,14 +3103,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
goto out_unlock;
}
+again:
ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
if (ret)
goto out_unlock;
if (same_inode)
- lock_extent_range(src, same_lock_start, same_lock_len);
+ ret = lock_extent_range(src, same_lock_start, same_lock_len,
+ false);
else
- btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+ ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len,
+ false);
+ /*
+ * If one of the inodes has dirty pages in the respective range or
+ * ordered extents, we need to flush dellaloc and wait for all ordered
+ * extents in the range. We must unlock the pages and the ranges in the
+ * io trees to avoid deadlocks when flushing delalloc (requires locking
+ * pages) and when waiting for ordered extents to complete (they require
+ * range locking).
+ */
+ if (ret == -EAGAIN) {
+ /*
+ * Ranges in the io trees already unlocked. Now unlock all
+ * pages before waiting for all IO to complete.
+ */
+ btrfs_cmp_data_free(&cmp);
+ if (same_inode) {
+ btrfs_wait_ordered_range(src, same_lock_start,
+ same_lock_len);
+ } else {
+ btrfs_wait_ordered_range(src, loff, len);
+ btrfs_wait_ordered_range(dst, dst_loff, len);
+ }
+ goto again;
+ }
+ ASSERT(ret == 0);
+ if (WARN_ON(ret)) {
+ /* ranges in the io trees already unlocked */
+ btrfs_cmp_data_free(&cmp);
+ return ret;
+ }
/* pass original length for comparison so we stay within i_size */
ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
@@ -3895,9 +3964,15 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
u64 lock_start = min_t(u64, off, destoff);
u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
- lock_extent_range(src, lock_start, lock_len);
+ ret = lock_extent_range(src, lock_start, lock_len, true);
} else {
- btrfs_double_extent_lock(src, off, inode, destoff, len);
+ ret = btrfs_double_extent_lock(src, off, inode, destoff, len,
+ true);
+ }
+ ASSERT(ret == 0);
+ if (WARN_ON(ret)) {
+ /* ranges in the io trees already unlocked */
+ goto out_unlock;
}
ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a23399e8e..9e084477d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1257,6 +1257,15 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction,
int ret;
int slot;
struct extent_buffer *l;
+ u64 min_search_start;
+
+ /*
+ * We don't want to overwrite the superblock on the drive nor any area
+ * used by the boot loader (grub for example), so we make sure to start
+ * at an offset of at least 1MB.
+ */
+ min_search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
+ search_start = max(search_start, min_search_start);
path = btrfs_alloc_path();
if (!path)
@@ -1397,18 +1406,9 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
struct btrfs_device *device, u64 num_bytes,
u64 *start, u64 *len)
{
- struct btrfs_root *root = device->dev_root;
- u64 search_start;
-
/* FIXME use last free of some kind */
-
- /*
- * we don't want to overwrite the superblock on the drive,
- * so we make sure to start at an offset of at least 1MB
- */
- search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
return find_free_dev_extent_start(trans->transaction, device,
- num_bytes, search_start, start, len);
+ num_bytes, 0, start, len);
}
static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
@@ -6512,6 +6512,14 @@ int btrfs_read_sys_array(struct btrfs_root *root)
goto out_short_read;
num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+ if (!num_stripes) {
+ printk(KERN_ERR
+ "BTRFS: invalid number of stripes %u in sys_array at offset %u\n",
+ num_stripes, cur_offset);
+ ret = -EIO;
+ break;
+ }
+
len = btrfs_chunk_item_size(num_stripes);
if (cur_offset + len > array_size)
goto out_short_read;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 7febcf247..50b268483 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -50,7 +50,7 @@ void cifs_vfs_err(const char *fmt, ...)
vaf.fmt = fmt;
vaf.va = &args;
- pr_err("CIFS VFS: %pV", &vaf);
+ pr_err_ratelimited("CIFS VFS: %pV", &vaf);
va_end(args);
}
diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h
index f40fbaca1..66cf0f9ff 100644
--- a/fs/cifs/cifs_debug.h
+++ b/fs/cifs/cifs_debug.h
@@ -51,14 +51,13 @@ __printf(1, 2) void cifs_vfs_err(const char *fmt, ...);
/* information message: e.g., configuration, major event */
#define cifs_dbg(type, fmt, ...) \
do { \
- if (type == FYI) { \
- if (cifsFYI & CIFS_INFO) { \
- pr_debug("%s: " fmt, __FILE__, ##__VA_ARGS__); \
- } \
+ if (type == FYI && cifsFYI & CIFS_INFO) { \
+ pr_debug_ratelimited("%s: " \
+ fmt, __FILE__, ##__VA_ARGS__); \
} else if (type == VFS) { \
cifs_vfs_err(fmt, ##__VA_ARGS__); \
} else if (type == NOISY && type != 0) { \
- pr_debug(fmt, ##__VA_ARGS__); \
+ pr_debug_ratelimited(fmt, ##__VA_ARGS__); \
} \
} while (0)
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index afa09fce8..e682b36a2 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -714,7 +714,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL);
if (!ses->auth_key.response) {
- rc = ENOMEM;
+ rc = -ENOMEM;
ses->auth_key.len = 0;
goto setup_ntlmv2_rsp_ret;
}
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index ecb0803bd..3c194ff0d 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -368,7 +368,6 @@ cifs_reconnect(struct TCP_Server_Info *server)
server->session_key.response = NULL;
server->session_key.len = 0;
server->lstrp = jiffies;
- mutex_unlock(&server->srv_mutex);
/* mark submitted MIDs for retry and issue callback */
INIT_LIST_HEAD(&retry_list);
@@ -381,6 +380,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
list_move(&mid_entry->qhead, &retry_list);
}
spin_unlock(&GlobalMid_Lock);
+ mutex_unlock(&server->srv_mutex);
cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__);
list_for_each_safe(tmp, tmp2, &retry_list) {
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 0557c45e9..b30a4a6d9 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -847,6 +847,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
* if buggy server returns . and .. late do we want to
* check for that here?
*/
+ *tmp_buf = 0;
rc = cifs_filldir(current_entry, file, ctx,
tmp_buf, max_len);
if (rc) {
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 2a24c524f..87abe8ed0 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -576,14 +576,16 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
cifs_in_send_dec(server);
cifs_save_when_sent(mid);
- if (rc < 0)
+ if (rc < 0) {
server->sequence_number -= 2;
+ cifs_delete_mid(mid);
+ }
+
mutex_unlock(&server->srv_mutex);
if (rc == 0)
return 0;
- cifs_delete_mid(mid);
add_credits_and_wake_if(server, credits, optype);
return rc;
}
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index c35ffdc12..706de324f 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
mutex_unlock(&allocated_ptys_lock);
}
+/*
+ * pty code needs to hold extra references in case of last /dev/tty close
+ */
+
+void devpts_add_ref(struct inode *ptmx_inode)
+{
+ struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+ atomic_inc(&sb->s_active);
+ ihold(ptmx_inode);
+}
+
+void devpts_del_ref(struct inode *ptmx_inode)
+{
+ struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+ iput(ptmx_inode);
+ deactivate_super(sb);
+}
+
/**
* devpts_pty_new -- create a new inode in /dev/pts/
* @ptmx_inode: inode of the master
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index ec0668a60..fe1f50fe7 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
- ext4_error(sb, "Checksum bad for group %u", block_group);
grp = ext4_get_group_info(sb, block_group);
if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
}
ext4_lock_group(sb, block_group);
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-
err = ext4_init_block_bitmap(sb, bh, block_group, desc);
set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
ext4_unlock_group(sb, block_group);
unlock_buffer(bh);
- if (err)
+ if (err) {
+ ext4_error(sb, "Failed to init block bitmap for group "
+ "%u: %d", block_group, err);
goto out;
+ }
goto verify;
}
ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 1b8024d26..53f2b98a6 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb,
/* If checksum is bad mark all blocks and inodes use to prevent
* allocation, essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
- ext4_error(sb, "Checksum bad for group %u", block_group);
grp = ext4_get_group_info(sb, block_group);
if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
set_buffer_verified(bh);
ext4_unlock_group(sb, block_group);
unlock_buffer(bh);
- if (err)
+ if (err) {
+ ext4_error(sb, "Failed to init inode bitmap for group "
+ "%u: %d", block_group, err);
goto out;
+ }
return bh;
}
ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index fb6f11709..e032a0423 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
ext4_lblk_t orig_blk_offset, donor_blk_offset;
unsigned long blocksize = orig_inode->i_sb->s_blocksize;
unsigned int tmp_data_size, data_size, replaced_size;
- int err2, jblocks, retries = 0;
+ int i, err2, jblocks, retries = 0;
int replaced_count = 0;
int from = data_offset_in_page << orig_inode->i_blkbits;
int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
struct super_block *sb = orig_inode->i_sb;
+ struct buffer_head *bh = NULL;
/*
* It needs twice the amount of ordinary journal buffers because
@@ -380,8 +381,16 @@ data_copy:
}
/* Perform all necessary steps similar write_begin()/write_end()
* but keeping in mind that i_size will not change */
- *err = __block_write_begin(pagep[0], from, replaced_size,
- ext4_get_block);
+ if (!page_has_buffers(pagep[0]))
+ create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0);
+ bh = page_buffers(pagep[0]);
+ for (i = 0; i < data_offset_in_page; i++)
+ bh = bh->b_this_page;
+ for (i = 0; i < block_len_in_page; i++) {
+ *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
+ if (*err < 0)
+ break;
+ }
if (!*err)
*err = block_commit_write(pagep[0], from, from + replaced_size);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ad62d7acc..34038e359 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
if (flex_gd == NULL)
goto out3;
- if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
+ if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
goto out2;
flex_gd->count = flexbg_size;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index de4bdfac0..595ebdb41 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -463,6 +463,7 @@ hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end)
*/
vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) {
unsigned long v_offset;
+ unsigned long v_end;
/*
* Can the expression below overflow on 32-bit arches?
@@ -475,15 +476,17 @@ hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end)
else
v_offset = 0;
- if (end) {
- end = ((end - start) << PAGE_SHIFT) +
- vma->vm_start + v_offset;
- if (end > vma->vm_end)
- end = vma->vm_end;
- } else
- end = vma->vm_end;
+ if (!end)
+ v_end = vma->vm_end;
+ else {
+ v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT)
+ + vma->vm_start;
+ if (v_end > vma->vm_end)
+ v_end = vma->vm_end;
+ }
- unmap_hugepage_range(vma, vma->vm_start + v_offset, end, NULL);
+ unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end,
+ NULL);
}
}
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 03516c808..2a2e2d8dd 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -145,7 +145,7 @@ static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
return false;
for (i = 0; i < m1->fh_versions_cnt; i++) {
bool found_fh = false;
- for (j = 0; j < m2->fh_versions_cnt; i++) {
+ for (j = 0; j < m2->fh_versions_cnt; j++) {
if (nfs_compare_fh(&m1->fh_versions[i],
&m2->fh_versions[j]) == 0) {
found_fh = true;
@@ -1859,11 +1859,9 @@ ff_layout_encode_layoutreturn(struct pnfs_layout_hdr *lo,
start = xdr_reserve_space(xdr, 4);
BUG_ON(!start);
- if (ff_layout_encode_ioerr(flo, xdr, args))
- goto out;
-
+ ff_layout_encode_ioerr(flo, xdr, args);
ff_layout_encode_iostats(flo, xdr, args);
-out:
+
*start = cpu_to_be32((xdr->p - start - 1) * 4);
dprintk("%s: Return\n", __func__);
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c7e8b87da..3e2071a17 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1641,6 +1641,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
unsigned long invalid = 0;
unsigned long now = jiffies;
unsigned long save_cache_validity;
+ bool cache_revalidated = true;
dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
__func__, inode->i_sb->s_id, inode->i_ino,
@@ -1702,22 +1703,28 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfs_force_lookup_revalidate(inode);
inode->i_version = fattr->change_attr;
}
- } else
+ } else {
nfsi->cache_validity |= save_cache_validity;
+ cache_revalidated = false;
+ }
if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
- } else if (server->caps & NFS_CAP_MTIME)
+ } else if (server->caps & NFS_CAP_MTIME) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_FORCED);
+ cache_revalidated = false;
+ }
if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
- } else if (server->caps & NFS_CAP_CTIME)
+ } else if (server->caps & NFS_CAP_CTIME) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_FORCED);
+ cache_revalidated = false;
+ }
/* Check if our cached file size is stale */
if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
@@ -1737,19 +1744,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
(long long)cur_isize,
(long long)new_isize);
}
- } else
+ } else {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_PAGECACHE
| NFS_INO_REVAL_FORCED);
+ cache_revalidated = false;
+ }
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
- else if (server->caps & NFS_CAP_ATIME)
+ else if (server->caps & NFS_CAP_ATIME) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATIME
| NFS_INO_REVAL_FORCED);
+ cache_revalidated = false;
+ }
if (fattr->valid & NFS_ATTR_FATTR_MODE) {
if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) {
@@ -1758,36 +1769,42 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
inode->i_mode = newmode;
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
}
- } else if (server->caps & NFS_CAP_MODE)
+ } else if (server->caps & NFS_CAP_MODE) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
+ cache_revalidated = false;
+ }
if (fattr->valid & NFS_ATTR_FATTR_OWNER) {
if (!uid_eq(inode->i_uid, fattr->uid)) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_uid = fattr->uid;
}
- } else if (server->caps & NFS_CAP_OWNER)
+ } else if (server->caps & NFS_CAP_OWNER) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
+ cache_revalidated = false;
+ }
if (fattr->valid & NFS_ATTR_FATTR_GROUP) {
if (!gid_eq(inode->i_gid, fattr->gid)) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_gid = fattr->gid;
}
- } else if (server->caps & NFS_CAP_OWNER_GROUP)
+ } else if (server->caps & NFS_CAP_OWNER_GROUP) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
+ cache_revalidated = false;
+ }
if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
if (inode->i_nlink != fattr->nlink) {
@@ -1796,19 +1813,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
invalid |= NFS_INO_INVALID_DATA;
set_nlink(inode, fattr->nlink);
}
- } else if (server->caps & NFS_CAP_NLINK)
+ } else if (server->caps & NFS_CAP_NLINK) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_FORCED);
+ cache_revalidated = false;
+ }
if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
/*
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
- }
- if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
+ } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
inode->i_blocks = fattr->du.nfs2.blocks;
+ else
+ cache_revalidated = false;
/* Update attrtimeo value if we're out of the unstable period */
if (invalid & NFS_INO_INVALID_ATTR) {
@@ -1818,9 +1838,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
/* Set barrier to be more recent than all outstanding updates */
nfsi->attr_gencount = nfs_inc_attr_generation_counter();
} else {
- if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
- if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode))
- nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
+ if (cache_revalidated) {
+ if (!time_in_range_open(now, nfsi->attrtimeo_timestamp,
+ nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
+ nfsi->attrtimeo <<= 1;
+ if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode))
+ nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
+ }
nfsi->attrtimeo_timestamp = now;
}
/* Set the barrier to be more recent than this fattr */
@@ -1829,7 +1853,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
}
/* Don't declare attrcache up to date if there were no attrs! */
- if (fattr->valid != 0)
+ if (cache_revalidated)
invalid &= ~NFS_INO_INVALID_ATTR;
/* Don't invalidate the data if we were to blame */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 343b0f1f1..f496ed721 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1385,6 +1385,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s
* Protect the call to nfs4_state_set_mode_locked and
* serialise the stateid update
*/
+ spin_lock(&state->owner->so_lock);
write_seqlock(&state->seqlock);
if (deleg_stateid != NULL) {
nfs4_stateid_copy(&state->stateid, deleg_stateid);
@@ -1393,7 +1394,6 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s
if (open_stateid != NULL)
nfs_set_open_stateid_locked(state, open_stateid, fmode);
write_sequnlock(&state->seqlock);
- spin_lock(&state->owner->so_lock);
update_open_stateflags(state, fmode);
spin_unlock(&state->owner->so_lock);
}
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 0a8983492..eff6319d5 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -22,9 +22,9 @@
int ovl_copy_xattr(struct dentry *old, struct dentry *new)
{
- ssize_t list_size, size;
- char *buf, *name, *value;
- int error;
+ ssize_t list_size, size, value_size = 0;
+ char *buf, *name, *value = NULL;
+ int uninitialized_var(error);
if (!old->d_inode->i_op->getxattr ||
!new->d_inode->i_op->getxattr)
@@ -41,29 +41,40 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
if (!buf)
return -ENOMEM;
- error = -ENOMEM;
- value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL);
- if (!value)
- goto out;
-
list_size = vfs_listxattr(old, buf, list_size);
if (list_size <= 0) {
error = list_size;
- goto out_free_value;
+ goto out;
}
for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
- size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX);
- if (size <= 0) {
+retry:
+ size = vfs_getxattr(old, name, value, value_size);
+ if (size == -ERANGE)
+ size = vfs_getxattr(old, name, NULL, 0);
+
+ if (size < 0) {
error = size;
- goto out_free_value;
+ break;
+ }
+
+ if (size > value_size) {
+ void *new;
+
+ new = krealloc(value, size, GFP_KERNEL);
+ if (!new) {
+ error = -ENOMEM;
+ break;
+ }
+ value = new;
+ value_size = size;
+ goto retry;
}
+
error = vfs_setxattr(new, name, value, size, 0);
if (error)
- goto out_free_value;
+ break;
}
-
-out_free_value:
kfree(value);
out:
kfree(buf);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 4060ffde8..b29036aa8 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -42,6 +42,19 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
int err;
struct dentry *upperdentry;
+ /*
+ * Check for permissions before trying to copy-up. This is redundant
+ * since it will be rechecked later by ->setattr() on upper dentry. But
+ * without this, copy-up can be triggered by just about anybody.
+ *
+ * We don't initialize inode->size, which just means that
+ * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
+ * check for a swapfile (which this won't be anyway).
+ */
+ err = inode_change_ok(dentry->d_inode, attr);
+ if (err)
+ return err;
+
err = ovl_want_write(dentry);
if (err)
goto out;
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 70e9af551..adcb1398c 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -571,7 +571,8 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
(int) PTR_ERR(dentry));
continue;
}
- ovl_cleanup(upper->d_inode, dentry);
+ if (dentry->d_inode)
+ ovl_cleanup(upper->d_inode, dentry);
dput(dentry);
}
mutex_unlock(&upper->d_inode->i_mutex);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index e38ee0fed..f42c9407f 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -9,6 +9,7 @@
#include <linux/fs.h>
#include <linux/namei.h>
+#include <linux/pagemap.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/mount.h>
@@ -910,6 +911,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
}
sb->s_stack_depth = 0;
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
if (ufs->config.upperdir) {
if (!ufs->config.workdir) {
pr_err("overlayfs: missing 'workdir'\n");
@@ -1053,6 +1055,9 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
root_dentry->d_fsdata = oe;
+ ovl_copyattr(ovl_dentry_real(root_dentry)->d_inode,
+ root_dentry->d_inode);
+
sb->s_magic = OVERLAYFS_SUPER_MAGIC;
sb->s_op = &ovl_super_operations;
sb->s_root = root_dentry;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index d73291f5f..b6c00ce0e 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -395,7 +395,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
state = *get_task_state(task);
vsize = eip = esp = 0;
- permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT);
+ permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT);
mm = get_task_mm(task);
if (mm) {
vsize = task_vsize(mm);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index aa41f2a7b..8be0e4cd2 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -403,7 +403,7 @@ static const struct file_operations proc_pid_cmdline_ops = {
static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
+ struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (mm && !IS_ERR(mm)) {
unsigned int nwords = 0;
do {
@@ -430,7 +430,8 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
wchan = get_wchan(task);
- if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname))
+ if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)
+ && !lookup_symbol_name(wchan, symname))
seq_printf(m, "%s", symname);
else
seq_putc(m, '0');
@@ -444,7 +445,7 @@ static int lock_trace(struct task_struct *task)
int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
if (err)
return err;
- if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
mutex_unlock(&task->signal->cred_guard_mutex);
return -EPERM;
}
@@ -697,7 +698,7 @@ static int proc_fd_access_allowed(struct inode *inode)
*/
task = get_proc_task(inode);
if (task) {
- allowed = ptrace_may_access(task, PTRACE_MODE_READ);
+ allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
put_task_struct(task);
}
return allowed;
@@ -732,7 +733,7 @@ static bool has_pid_permissions(struct pid_namespace *pid,
return true;
if (in_group_p(pid->pid_gid))
return true;
- return ptrace_may_access(task, PTRACE_MODE_READ);
+ return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
}
@@ -809,7 +810,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
struct mm_struct *mm = ERR_PTR(-ESRCH);
if (task) {
- mm = mm_access(task, mode);
+ mm = mm_access(task, mode | PTRACE_MODE_FSCREDS);
put_task_struct(task);
if (!IS_ERR_OR_NULL(mm)) {
@@ -1856,7 +1857,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
if (!task)
goto out_notask;
- mm = mm_access(task, PTRACE_MODE_READ);
+ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (IS_ERR_OR_NULL(mm))
goto out;
@@ -2007,7 +2008,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
goto out;
result = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
result = -ENOENT;
@@ -2060,7 +2061,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
goto out;
ret = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
ret = 0;
@@ -2530,7 +2531,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
if (result)
return result;
- if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
result = -EACCES;
goto out_unlock;
}
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index f6e8354b8..1b0ea4a5d 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -42,7 +42,7 @@ static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie)
if (!task)
return error;
- if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
error = ns_get_path(&ns_path, task, ns_ops);
if (!error)
nd_jump_link(&ns_path);
@@ -63,7 +63,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
if (!task)
return res;
- if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
res = ns_get_name(name, sizeof(name), task, ns_ops);
if (res >= 0)
res = readlink_copy(buffer, buflen, name);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e03793e75..e4733feb0 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1476,18 +1476,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long end, struct mm_walk *walk)
{
+ pte_t huge_pte = huge_ptep_get(pte);
struct numa_maps *md;
struct page *page;
- if (!pte_present(*pte))
+ if (!pte_present(huge_pte))
return 0;
- page = pte_page(*pte);
+ page = pte_page(huge_pte);
if (!page)
return 0;
md = walk->private;
- gather_stats(page, md, pte_dirty(*pte), 1);
+ gather_stats(page, md, pte_dirty(huge_pte), 1);
return 0;
}
diff --git a/fs/timerfd.c b/fs/timerfd.c
index b94fa6c3c..053818dd6 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -153,7 +153,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
if (isalarm(ctx))
remaining = alarm_expires_remaining(&ctx->t.alarm);
else
- remaining = hrtimer_expires_remaining(&ctx->t.tmr);
+ remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr);
return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
}
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 8d0b3ade0..566df9b5a 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -2047,14 +2047,29 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos,
epos->offset += adsize;
}
+/*
+ * Only 1 indirect extent in a row really makes sense but allow upto 16 in case
+ * someone does some weird stuff.
+ */
+#define UDF_MAX_INDIR_EXTS 16
+
int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
struct kernel_lb_addr *eloc, uint32_t *elen, int inc)
{
int8_t etype;
+ unsigned int indirections = 0;
while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) ==
(EXT_NEXT_EXTENT_ALLOCDECS >> 30)) {
int block;
+
+ if (++indirections > UDF_MAX_INDIR_EXTS) {
+ udf_err(inode->i_sb,
+ "too many indirect extents in inode %lu\n",
+ inode->i_ino);
+ return -1;
+ }
+
epos->block = *eloc;
epos->offset = sizeof(struct allocExtDesc);
brelse(epos->bh);
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index ab478e62b..e788a05aa 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -128,11 +128,15 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i)
if (c < 0x80U)
utf_o->u_name[utf_o->u_len++] = (uint8_t)c;
else if (c < 0x800U) {
+ if (utf_o->u_len > (UDF_NAME_LEN - 4))
+ break;
utf_o->u_name[utf_o->u_len++] =
(uint8_t)(0xc0 | (c >> 6));
utf_o->u_name[utf_o->u_len++] =
(uint8_t)(0x80 | (c & 0x3f));
} else {
+ if (utf_o->u_len > (UDF_NAME_LEN - 5))
+ break;
utf_o->u_name[utf_o->u_len++] =
(uint8_t)(0xe0 | (c >> 12));
utf_o->u_name[utf_o->u_len++] =
@@ -173,17 +177,22 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i)
static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length)
{
unsigned c, i, max_val, utf_char;
- int utf_cnt, u_len;
+ int utf_cnt, u_len, u_ch;
memset(ocu, 0, sizeof(dstring) * length);
ocu[0] = 8;
max_val = 0xffU;
+ u_ch = 1;
try_again:
u_len = 0U;
utf_char = 0U;
utf_cnt = 0U;
for (i = 0U; i < utf->u_len; i++) {
+ /* Name didn't fit? */
+ if (u_len + 1 + u_ch >= length)
+ return 0;
+
c = (uint8_t)utf->u_name[i];
/* Complete a multi-byte UTF-8 character */
@@ -225,6 +234,7 @@ try_again:
if (max_val == 0xffU) {
max_val = 0xffffU;
ocu[0] = (uint8_t)0x10U;
+ u_ch = 2;
goto try_again;
}
goto error_out;
@@ -277,7 +287,7 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o,
c = (c << 8) | ocu[i++];
len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len],
- UDF_NAME_LEN - utf_o->u_len);
+ UDF_NAME_LEN - 2 - utf_o->u_len);
/* Valid character? */
if (len >= 0)
utf_o->u_len += len;
@@ -295,15 +305,19 @@ static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni,
int len;
unsigned i, max_val;
uint16_t uni_char;
- int u_len;
+ int u_len, u_ch;
memset(ocu, 0, sizeof(dstring) * length);
ocu[0] = 8;
max_val = 0xffU;
+ u_ch = 1;
try_again:
u_len = 0U;
for (i = 0U; i < uni->u_len; i++) {
+ /* Name didn't fit? */
+ if (u_len + 1 + u_ch >= length)
+ return 0;
len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char);
if (!len)
continue;
@@ -316,6 +330,7 @@ try_again:
if (uni_char > max_val) {
max_val = 0xffffU;
ocu[0] = (uint8_t)0x10U;
+ u_ch = 2;
goto try_again;
}
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 8774498ce..e2536bb1c 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -786,7 +786,7 @@ typedef struct xfs_agfl {
__be64 agfl_lsn;
__be32 agfl_crc;
__be32 agfl_bno[]; /* actually XFS_AGFL_SIZE(mp) */
-} xfs_agfl_t;
+} __attribute__((packed)) xfs_agfl_t;
#define XFS_AGFL_CRC_OFF offsetof(struct xfs_agfl, agfl_crc)
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 268c00f4f..65485cfc4 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -62,11 +62,12 @@ xfs_inobp_check(
* has not had the inode cores stamped into it. Hence for readahead, the buffer
* may be potentially invalid.
*
- * If the readahead buffer is invalid, we don't want to mark it with an error,
- * but we do want to clear the DONE status of the buffer so that a followup read
- * will re-read it from disk. This will ensure that we don't get an unnecessary
- * warnings during log recovery and we don't get unnecssary panics on debug
- * kernels.
+ * If the readahead buffer is invalid, we need to mark it with an error and
+ * clear the DONE status of the buffer so that a followup read will re-read it
+ * from disk. We don't report the error otherwise to avoid warnings during log
+ * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
+ * because all we want to do is say readahead failed; there is no-one to report
+ * the error to, so this will distinguish it from a non-ra verifier failure.
*/
static void
xfs_inode_buf_verify(
@@ -93,6 +94,7 @@ xfs_inode_buf_verify(
XFS_RANDOM_ITOBP_INOTOBP))) {
if (readahead) {
bp->b_flags &= ~XBF_DONE;
+ xfs_buf_ioerror(bp, -EIO);
return;
}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 3243cdf97..39090fc56 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -604,6 +604,13 @@ found:
}
}
+ /*
+ * Clear b_error if this is a lookup from a caller that doesn't expect
+ * valid data to be found in the buffer.
+ */
+ if (!(flags & XBF_READ))
+ xfs_buf_ioerror(bp, 0);
+
XFS_STATS_INC(target->bt_mount, xb_get);
trace_xfs_buf_get(bp, flags, _RET_IP_);
return bp;
@@ -1520,6 +1527,16 @@ xfs_wait_buftarg(
LIST_HEAD(dispose);
int loop = 0;
+ /*
+ * We need to flush the buffer workqueue to ensure that all IO
+ * completion processing is 100% done. Just waiting on buffer locks is
+ * not sufficient for async IO as the reference count held over IO is
+ * not released until after the buffer lock is dropped. Hence we need to
+ * ensure here that all reference counts have been dropped before we
+ * start walking the LRU list.
+ */
+ drain_workqueue(btp->bt_mount->m_buf_workqueue);
+
/* loop until there is nothing left on the lru list. */
while (list_lru_count(&btp->bt_lru)) {
list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele,